Weihang Xia

Papers

Total Citations

H-Index

About

Weihang Xia is a rising researcher at the forefront of multi-agent robotics and geometric deep learning, with a focus on decentralized decision-making in complex environments. His most influential work, “SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding” (2025), introduces a novel framework that leverages sheaf theory—a branch of algebraic topology—to model local interactions and global constraints in multi-agent pathfinding (MAPF). This approach enables agents to learn collision-free, shortest paths in obstacle-ridden settings without centralized coordination, a critical advance for large-scale logistics and autonomous transportation. Though early in its trajectory, the paper has already garnered 2 citations, signaling growing interest in Xia’s innovative synthesis of geometric methods and reinforcement learning. His contributions address a core bottleneck in robotics: scaling decentralized planning to hundreds of agents while maintaining efficiency and safety. By bridging topology and multi-agent systems, Xia is carving a niche that could reshape how robots navigate warehouses, factories, and urban spaces. For students and researchers, his work exemplifies how interdisciplinary thinking—merging abstract mathematics with practical engineering—can unlock new solutions to longstanding challenges in robotics and AI.